summaryrefslogtreecommitdiff
path: root/src/gallium/drivers/nvc0
AgeCommit message (Collapse)Author
2011-02-09nvc0: replace branching with predicated insns where feasibleChristoph Bumiller
2011-02-09nvc0: implement local memory load and store opsChristoph Bumiller
2011-02-09nvc0: make sure phi-ops really have one source per in-blockChristoph Bumiller
2011-02-09nv50,nvc0: do not forget to apply sign mode to saved TGSI inputsChristoph Bumiller
2011-02-09nvc0: do not generate a backwards jump if a loop ends with BRKChristoph Bumiller
2011-02-09nvc0: store only one value per basic block for TGSI regsChristoph Bumiller
2011-02-09nv50,nvc0: fix condition code change when commuting SET sourcesChristoph Bumiller
2011-02-09nvc0: set basic block on manual instruction insertionChristoph Bumiller
2011-02-09nvc0: try to fix register conflicts for vector instructionsChristoph Bumiller
Vector here means using multiple 32 bit regs which are forced to be consecutive in the register file. This still isn't quite nice.
2011-02-09nvc0: reset texture base address after read transferChristoph Bumiller
2011-02-09nvc0: don't combine memory loads across block boundariesChristoph Bumiller
2011-02-09nvc0: detect no-op MIN/MAX, do CSE earlier to succeed more oftenChristoph Bumiller
2011-01-30nvc0: implement transform feedback stateChristoph Bumiller
2011-01-29nvc0: enable PIPE_CAP_ARRAY_TEXTURES and fix themChristoph Bumiller
2011-01-24nvc0: Move declaration before code.Vinson Lee
Fixes nvc0 SCons build.
2011-01-23nvc0: implement point coord replacementChristoph Bumiller
But we have to cheat and peek at the GENERIC semantic indices the state tracker uses for TEXn. Only outputs from 0x300 to 0x37c can be replaced, and so we have to know on shader compilation which ones to put there in order to keep doing separate shader objects properly. At some point I'll probably create a patch that makes gallium not force us to discard the information about what is a TexCoord.
2011-01-23nvc0: fix emit_cvt for ceil, floor and truncChristoph Bumiller
2011-01-23nvc0: remove bad assert and emit TEMP movs insteadChristoph Bumiller
2011-01-23nvc0: fix address and value slot assignment in load combiningChristoph Bumiller
2011-01-23nvc0: don't omit highest bit of branch targetChristoph Bumiller
Fixes negative relative branch offsets.
2011-01-23nvc0: recognize r63 as zero in constant foldingChristoph Bumiller
2011-01-23nvc0: add MARK_RING where missing to avoid too many relocs errorsChristoph Bumiller
2011-01-23nvc0: don't apply base vertex to per-instance arraysChristoph Bumiller
2011-01-23nvc0: commute sources of SET too if beneficialChristoph Bumiller
2011-01-23nvc0: accept neg abs modifiers on lg2Christoph Bumiller
2011-01-17nouveau: fix build against out of tree libdrmDave Airlie
For doing builds against a separated libdrm these cflags are needed. Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-01-16nvc0: fix and enable instanced drawing and arraysChristoph Bumiller
2011-01-15nvc0: try to swap immediates to first source tooChristoph Bumiller
2011-01-15nvc0: make sure all sources of the BIND op are distinctChristoph Bumiller
They're supposed to be assigned consecutive registers so they can't contain the same SSA value more than once.
2011-01-15nvc0: update user vbufs on each draw callChristoph Bumiller
This is required in case set_vertex_buffers is not called again.
2011-01-15nvc0: enable early fragment tests where possibleChristoph Bumiller
2011-01-15nvc0: upload small buffers through the command bufferChristoph Bumiller
2011-01-13nvc0: identify POINT_RASTER_RULES, add POINT_SMOOTH stateChristoph Bumiller
Point smoothing requires rasterization rules to be set to OGL. Sorry for the extra noise caused by the header update.
2011-01-13nvc0: disable calling of sw methods we don't implementBen Skeggs
Left in the code as a marker of what NVIDIA do, just in case we need to do this some day. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-01-13nvc0: fix mp_stack_bo relocationBen Skeggs
Fixes a PT_NOT_PRESENT error cause by: - allocating in VRAM - emitting GART relocs to 0x17bc/0x17c0, moving the buffer - telling the bufmgr that the buffer should be in VRAM when we use it, but not correcting the value sent to 0x17bc/0x17c0. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-01-09nvc0: implement queriesChristoph Bumiller
2011-01-08nvc0: fix primitive restart in immediate modeChristoph Bumiller
2011-01-08nvc0: fix reloc domain conflict on buffer migrationChristoph Bumiller
Occurred because the code assumed that buf->domain would remain equal to old_domain.
2011-01-08nvc0: upload user buffers only from draw info min to max indexChristoph Bumiller
There are actually applications that profit immensely from this.
2011-01-08nvc0: fix emission of first 3 u8 indices to RING_NIChristoph Bumiller
2011-01-08nvc0: reset mt transfer address after read loop over layersChristoph Bumiller
2011-01-08nvc0: tie buffer memory release to the buffer fenceChristoph Bumiller
... instead of the next fence to be emitted. This way we have a chance to reclaim the storage earlier.
2011-01-06nvc0: Fix typo of nvc0_mm.c in SConscript.Vinson Lee
2011-01-04nvc0: fix index size method value for u8 indicesChristoph Bumiller
2011-01-04nvc0: set the correct FP header bit for multiple colour outputsChristoph Bumiller
2011-01-04nvc0: delete memory caches and fence on screen destructionChristoph Bumiller
2011-01-04nvc0: use mov instead of ld for scalar const loadsChristoph Bumiller
2011-01-04nvc0: fix resource unmap after vertex pushChristoph Bumiller
2011-01-04nvc0: use the proper typed opcodes in constant foldingChristoph Bumiller
2011-01-04nvc0: demagic GP invocation count bitfieldChristoph Bumiller
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-04 20:31:29 +0000